EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Distributionally Robust Multi-Agent Reinforcement Learning for Coordinated New-Type Power System Operation

Fei Liu, Outing Zhang, Jun Yin, Baomin Fang, Ruiming Fan, Zehua Xue, Zhongfu Tan

Energies · 17.07.2026 · 19 (14) · 3382

DOI: 10.3390/en19143382 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 17.07.2026. Verfasst von Fei Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Qinghai Electric Power Company.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High renewable penetration and large-scale green hydrogen production are accelerating the formation of the new-type power system (NTPS), in which electrical dispatch, electrolysis, hydrogen storage, fuel-cell reconversion, and flexible demand must be coordinated under nonlinear network physics and uncertain renewable, load, and hydrogen-demand trajectories. This study develops a physics-informed distributionally robust multi-agent reinforcement learning (PI-DRO-MARL) framework for coordinated NTPS operation with integrated electricity–hydrogen coupling. The operational objective is to minimize worst-case expected operating cost, including generation and grid-exchange cost, electrolysis and hydrogen-delivery cost, storage degradation, renewable curtailment, and load- or hydrogen-shedding penalties, while satisfying AC power-flow balance, voltage limits, line-loading limits, ramping limits, battery state-of-charge constraints, hydrogen-storage dynamics, and electrolysis/fuel-cell conversion constraints. The framework embeds physics-informed residuals and projection operators into a centralized-training decentralized-execution architecture; represents renewable, electrical-load, hydrogen-demand, and price uncertainty through statistically calibrated Wasserstein ambiguity sets; and trains agents with robust value estimation and feasibility-aware action correction. Validation is conducted on a modified IEEE 33-bus distribution network coupled with a 12-node hydrogen system, with additional scalability checks on modified IEEE 69-bus and IEEE 123-node reference systems. Across ten random seeds, the primary case shows an operating cost of USD 8850 with a 95% confidence interval of USD 8770–8940, a mean constraint-violation rate of 0.37%, and a shifted-scenario cost increase of 12.6%, outperforming deterministic optimization, stochastic programming, standard reinforcement learning (RL), proximal policy optimization (PPO), soft actor–critic (SAC), multi-agent deep deterministic policy gradient (MADDPG), constrained RL, safe RL, and robust RL baselines. Ablation, Wasserstein-radius, time-step, and stress-test analyses further show that distributional robustness, physics-informed projection, and multi-agent coordination provide distinct and complementary benefits. The results support PI-DRO-MARL as a simulation-validated architecture for real-time, uncertainty-aware NTPS dispatch, while field deployment still requires digital-twin calibration, hardware-in-the-loop testing, and site-specific operational validation.

Förderung

  • State Grid Qinghai Electric Power Company

Zitieren

APA

Liu, F., Zhang, O., Yin, J., Fang, B., Fan, R., Xue, Z., & Tan, Z. (2026). Physics-Informed Distributionally Robust Multi-Agent Reinforcement Learning for Coordinated New-Type Power System Operation. Energies, 19(14), 3382. https://doi.org/10.3390/en19143382

Vancouver

Liu F, Zhang O, Yin J, Fang B, Fan R, Xue Z, et al. Physics-Informed Distributionally Robust Multi-Agent Reinforcement Learning for Coordinated New-Type Power System Operation. Energies. 2026;19(14):3382. doi:10.3390/en19143382

BibTeX
@article{Liu2026,
  author = {Liu, Fei and Zhang, Outing and Yin, Jun and Fang, Baomin and Fan, Ruiming and Xue, Zehua and Tan, Zhongfu},
  title = {Physics-Informed Distributionally Robust Multi-Agent Reinforcement Learning for Coordinated New-Type Power System Operation},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {14},
  pages = {3382},
  doi = {10.3390/en19143382}
}
Kostenlos starten →